SLSB-forest:高维数据的近似k近邻查询

近似k近邻查询的研究一直受到广泛关注,局部敏感散列(LSH)是解决此问题的主流方法之一.LSH及目前大部分改进版本都会面临以下问题:数据散列以后在桶里分布不均匀;无法准确计算对应参数k的查询范围建立索引.基于此,将支持动态数据索引的LSH和B-tree结合,构建新的SLSB-forest索引结构,使散列桶里的数据维持在一个合理的区间.针对SLSB-forest提出了两种查询算法:快速查找和准确率优先查找,并通过理论和实验证明查找过程中查询范围的动态变化.     

基于多时-空相关的AVS2快速帧间预测算法

针对新一代视频标准AVS2引进四叉树分割、多参考帧等技术而带来的帧间预测复杂度增加的问题,提出一种基于多时-空相关的快速帧间预测算法.该算法利用上下层相邻编码单元(Coding Unit,CU)和空时域相邻CU在预测模式选择上的相关性,计算当前CU的模式复杂度,根据复杂度为当前CU分配合适的候选预测模式;同时利用相邻预测单元(Prediction Unit,PU)在参考帧选择上的相关性,计算当前PU的参考帧索引,根据索引为当前PU分配合适的候选参考帧.实验表明,该算法在BD-Rate(Bjontegaard delta bit rate)增加1.22％,BD-PSNR(Bjontegaard delta peak signal-to-noise rate)降低0.04 dB的前提下,平均减少47.54％的编码时间.     

基于直接线性变换法的视频图像解析

视频解析模拟人眼成像原理,利用安装在不同位置的2台摄像机拍摄的同一时刻同一场景的2幅视频图像,解析出三维坐标,以便计算机能够像人类一样理解现实世界。目前视频解析主要面临2个问题:设定标定物及解析算法和设置同步视频帧。由此出发,在对标定误差详细分析的基础上设计了新的标定物,根据标定物提出了一种垂直双平面解析算法,解决了标定物即解析算法问题;通过读取系统时间,把系统时间设定为帧的文件名解决了帧同步问题。实验对比证明了算法和技术的有效性。     

一种改进的H.264/AVC帧层码率控制算法

针对JVT-G012算法在帧层对P帧目标比特分配太过均匀,忽略了图像复杂度的问题,提出了一种简单有效的帧差比值法来进行帧层目标比特的分配,并利用缓冲区充盈度来调整当前帧量化参数的方法.通过大量实验仿真表明,与JVT-G012算法相比,该算法不仅能够更精确地控制码率,而且还提高了视频图像的质量.     

基于多帧边缘差异的视频运动对象的分割与跟踪算法

从视频场景中分割和跟踪感兴趣的视频对象对于MPEG-4等基于对象的视频编码来说是关键性的技术之一。针对目前大部分视频对象分割和追踪算法相当复杂但仍不能有效地去除背景噪声的问题,该文提出用于分割和跟踪视频运动对象的一种基于多帧边缘差异的算法。该算法利用一组帧的边缘差异来提取运动对象区域,通过聚类方法去除背景像素点,利用形态学算子得到对象分割模板,同时通过建立前帧感兴趣对象与当前帧运动对象的帧间向量跟踪当前帧的感兴趣视频对象。不同标准视频测试序列的测试结果表明,该算法能够实现对感兴趣的视频运动对象更为精确、快速和有效地分割和跟踪。     

一种基于区域Gibbs势能函数的视频运动对象分割算法

提出了一种基于时空联合分析框架的视频对象分割算法,通过改进的分水岭变换对视频图像进行帧内空间区域划分,并根据帧间运动信息和区域的空间特性得到初步的分割掩模;然后建立基于区域的马尔可夫随机场分布模型,并定义对应的Gibbs势能函数,通过迭代条件模式(ICM)方法求解得到最小化能量,从而获得稳定的分割标记场,准确地提取视频对象。实验结果表明,提出的分割算法性能优于欧洲COST211研究组所得到的分割结果。     

HR-Tree——一种基于P2P端点的XML树型索引方法

提出一种应用在P2P平台上的XML索引方法HR-Tree。HR-Tree索引方法首先利用区域划分的方法对于XML数据进行处理,再使用散列的方法把数据进行分类,最后利用HR-Tree树建立索引。和XR-Tree等索引方法相比,HR-Tree查询更为灵活,更能满足P2P各端点查询的要求。实验表明,该算法在XML数据的查询处理上是一个有效的方法。     

基于视频帧加权的台标自动检测方法

复杂背景切换以及半透明化趋势增加了电视台标检测的难度。针对当前台标检测中存在的问题,提出一种视频帧加权处理的台标自动检测方法。首先根据台标位置的先验知识,利用视频帧加权方法对视频图像帧作实时背景更新处理,得到稳定的灰度台标图像;然后采用Canny算法对实时灰度台标进行边缘检测,得到台标的轮廓图像;最后采用简化的分水岭填充算法得到单个台标图像。使用部分地方电视台台标进行实验,提取出的实时台标图像效果好,证明了该方法的有效性。     

基于超图排序算法的视频摘要

视频摘要技术作为一种快速感知视频内容的方式得到了广泛的关注.现有基于图模型的视频摘要方法将视频帧作为顶点,通过边表示两个顶点之间的关系,但并不能很好地捕获视频帧之间的复杂关系.为了克服该缺点,本文提出了一种基于超图排序算法的静态视频摘要方法（Hyper-Graph Ranking based Video Summarization,HGRVS）.HGRVS方法首先通过构建视频超图模型,将任意多个有内在关联的视频帧使用一条超边连接;然后提出一种基于超图排序的视频帧分类算法将视频帧按内容分类;最后通过求解提出的一种优化函数来生成静态视频摘要.在Open Video Project和YouTube两个数据集上的大量主观与客观实验验证了所提HGRVS算法的优良性能.     

一种可应用于大流量环境的双层散列算法研究

提出了一种可应用于大流量环境的双层散列算法,两个散列函数均直接作用于原始输入,键值散列函数用于产生可惟一表征原始输入的键值,下标散列函数用于产生键值在数据结构中的存储地址。针对上述两种需求给出了相应的算法评估测度,并通过实验从若干候选算法中选出较优的算法。实验表明,双层散列算法实用且有效,网络管理人员可将此算法应用于大流量环境,以减少网络中的冗余流量、过滤垃圾信息及进行流量分析。     

Video hashing with secondary frames and invariant moments

Video hashing is a useful technique of many multimedia systems, such as video copy detection, video authentication, tampering localization, video retrieval, and anti-privacy search. In this paper, we propose a novel video hashing with secondary frames and invariant moments. An important contribution is the secondary frame construction with 3D discrete wavelet transform, which can reach initial data compression and robustness against noise and compression. In addition, since invariant moments are robust and discriminative features, hash generation based on invariant moments extracted from secondary frames can ensure good classification of the proposed video hashing. Extensive experiments on 8300 videos are conducted to validate efficiency of the proposed video hashing. The results show that the proposed video hashing can resist many digital operations and has good discrimination. Performance comparisons with some state-of-the-art algorithms illustrate that the proposed video hashing outperforms the compared algorithms in classification in terms of receiver operating characteristic results.     

Deep multi-query video retrieval

Video retrieval methods have been developed for a single query. Multi-query video retrieval problem has not been investigated yet. In this study, an efficient and fast multi-query video retrieval framework is developed. Query videos are assumed to be related to more than one semantic. The framework supports an arbitrary number of video queries. The method is built upon using binary video hash codes. As a result, it is fast and requires a lower storage space. Database and query hash codes are generated by a deep hashing method that not only generates hash codes but also predicts query labels when they are chosen outside the database. The retrieval is based on the Pareto front multi-objective optimization method. Re-ranking performed on the retrieved videos by using non-binary deep features increases the retrieval accuracy considerably. Simulations carried out on two multi-label video databases show that the proposed method is efficient and fast in terms of retrieval accuracy and time.     

基于局部线性嵌入的视频拷贝检测方法

该文提出了基于局部线性嵌入(LLE)的视频哈希方法,该方法首先利用一个图模型选取代表帧,然后以四阶累积量作为视频在高维空间的特征并利用LLE对视频进行降维,利用视频在3维空间中投影点的范数构造视频哈希序列来实现视频拷贝检测。实验证明该方法具有较好的鲁棒性和区分性。     

Spline regression hashing for fast image search

Techniques for fast image retrieval over large databases have attracted considerable attention due to the rapid growth of web images. One promising way to accelerate image search is to use hashing technologies, which represent images by compact binary codewords. In this way, the similarity between images can be efficiently measured in terms of the Hamming distance between their corresponding binary codes. Although plenty of methods on generating hash codes have been proposed in recent years, there are still two key points that needed to be improved: 1) how to precisely preserve the similarity structure of the original data and 2) how to obtain the hash codes of the previously unseen data. In this paper, we propose our spline regression hashing method, in which both the local and global data similarity structures are exploited. To better capture the local manifold structure, we introduce splines developed in Sobolev space to find the local data mapping function. Furthermore, our framework simultaneously learns the hash codes of the training data and the hash function for the unseen data, which solves the out-of-sample problem. Extensive experiments conducted on real image datasets consisting of over one million images show that our proposed method outperforms the state-of-the-art techniques.     

Reduced frame set on wireless distorted video for quality assessment

Objective video quality assessment methods often evaluate all the frames regardless of their importance. For wireless distorted videos, not every frame has the same contribution to the final overall quality due to the channel fading and interference, which may lead to the capacity variation in temporal. Besides, with the content similarity and error propagation pattern in temporal domain, it is possible to evaluate the overall quality with only part of the frames. In this paper, a demonstration is performed to show that the video quality can be evaluated with reduced frames set (RFS), and a state transition model is proposed to extract the RFS. At last, a video quality assessment (VQA) method is carried out based on RFS. Compared with several state-of-the-art methods, our method can achieve a suitable accuracy with less frames to be processed.     

基于深度卷积神经网络和二进制哈希学习的图像检索方法

随着图像数据的迅猛增长,当前主流的图像检索方法采用的视觉特征编码步骤固定,缺少学习能力,导致其图像表达能力不强,而且视觉特征维数较高,严重制约了其图像检索性能。针对这些问题,该文提出一种基于深度卷积神径网络学习二进制哈希编码的方法,用于大规模的图像检索。该文的基本思想是在深度学习框架中增加一个哈希层,同时学习图像特征和哈希函数,且哈希函数满足独立性和量化误差最小的约束。首先,利用卷积神经网络强大的学习能力挖掘训练图像的内在隐含关系,提取图像深层特征,增强图像特征的区分性和表达能力。然后,将图像特征输入到哈希层,学习哈希函数使得哈希层输出的二进制哈希码分类误差和量化误差最小,且满足独立性约束。最后,给定输入图像通过该框架的哈希层得到相应的哈希码,从而可以在低维汉明空间中完成对大规模图像数据的有效检索。在3个常用数据集上的实验结果表明,利用所提方法得到哈希码,其图像检索性能优于当前主流方法。     

基于稀疏自编码的无监督哈希算法

最近邻搜索在大规模图像检索中变得越来越重要。在最近邻搜索中,许多哈希方法因为快速查询和低内存被提出。然而,现有方法在哈希函数构造过程中对数据稀疏结构研究的不足,本文提出了一种无监督的稀疏自编码的图像哈希方法。基于稀疏自编码的图像哈希方法将稀疏构造过程引入哈希函数的学习过程中,即通过利用稀疏自编码器的KL距离对哈希码进行稀疏约束以增强局部保持映射过程中的判别性,同时利用L2范数来哈希编码的量化误差。实验中用两个公共图像检索数据集CIFAR-10和YouTube Faces验证了本文算法相比其他无监督哈希算法的优越性。     

Consistent Picture Quality Control Strategy for Dependent Video Coding

Typically, a video rate control algorithm minimizes the average distortion (denoted as MINAVE) at the cost of large temporal quality variation, especially for videos with high motion and frequent scene changes. To alleviate the negative effect on subjective video quality, another criterion that restricts a small amount of quality variation among adjacent frames is preferred for practical applications. As pointed out by , although some existing proposals can produce consistent quality videos, they often fail to fully utilize the available bits to minimize the global total distortion. In this paper, we would like to achieve the triple goal of consistent quality video, minimizing the total distortion, and meeting the bit budget strictly all at the same time on the interframe dependent coding structure. Two approaches are taken to accomplish this goal. In the first algorithm, a trellis-based framework is proposed. One of our contributions is to derive an equivalent condition between the distortion minimization problem and the budget minimization problem. Second, our trellis state (tree node) is defined in terms of distortion, which facilitates the consistent quality control. Third, by adjusting one key parameter in our algorithm, a solution in between the MINAVE and the constant quality criteria can be obtained. The second approach is to combine the Lagrange multipliers method together with the consistent quality control. The PSNR performance is degraded slightly but the computational complexity is significantly reduced. Simulation results show that both our approaches produce a much smaller PSNR variation at a slight average PSNR loss as compared to the MPEG JM rate control. When they are compared to the other consistent quality proposals, only the proposed algorithms can strictly meet the target bit budget requirement (no more, no less) and produce the largest average PSNR at a small PSNR variation.     

Effective and efficient indexing in cross-modal hashing-based datasets

To overcome the barrier of storage and computation, the hashing technique has been widely used for nearest neighbor search in multimedia retrieval applications recently. Particularly, cross-modal retrieval that searches across different modalities becomes an active but challenging problem. Although numerous of cross-modal hashing algorithms are proposed to yield compact binary codes, exhaustive search is impractical for large-scale datasets, and Hamming distance computation suffers inaccurate results. In this paper, we propose a novel search method that utilizes a probability-based index scheme over binary hash codes in cross-modal retrieval. The proposed indexing scheme employs a few binary bits from the hash code as the index code. We construct an inverted index table based on the index codes, and train a neural network for ranking and indexing to improve the retrieval accuracy. Experiments are performed on two benchmark datasets for retrieval across image and text modalities, where hash codes are generated and compared with several state-of-the-art cross-modal hashing methods. Results show the proposed method effectively boosts the performance on search accuracy, computation cost, and memory consumption in these datasets and hashing methods. The source code is available on https://github.com/msarawut/HCI.